Cross-sell

TLDR

The study develops a product recommendation method for both online and surface mail promotions. The method uses a conditional‑independence assumption to pre‑compute probabilities, enabling fast, tunable recommendations evaluated on 17,400 customers at an online hardware retailer. The algorithm increased clickthrough by 40 %, revenue by 38 %, and units sold by 61 %, with further gains achievable through parameter tuning, highlighting its potential to boost retail promotion profitability.

Abstract

We develop a method for recommending products to customers with applications to both on-line and surface mail promotional offers. Our method differs from previous work in collaborative filtering [8] and imputation [18], in that we assume probabilities are conditionally independent. This assumption, which is also made in Naive Bayes [5], enables us to pre-compute probabilities and store them in main memory, enabling very fast performance on millions of customers. The algorithm supports a variety of tunable parameters so that the method can address different promotional objectives. We tested the algorithm at an on-line hardware retailer, with 17,400 customers divided randomly into control and experimental groups. In the experimental group, clickthrough increased by +40% (p<0.01), revenue by +38% (p<0.07), and units sold by +61% (p<0.01). By changing the algorithm’s parameter settings we found that these results could be improved even further. This work demonstrates the considerable potential of automated data mining for dramatically increasing the profitability of on and off-line retail promotions.